© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 13169
    Prev
    Next
    INDEX
    Explanations

    demonstrates/illustrates how to

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron primarily detects floating-point numerical values (decimal numbers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ры
    0.88
    ты
    0.87
    товый
    0.85
    祀
    0.85
    ⊟
    0.84
     electricity
    0.84
    ные
    0.83
     baseX
    0.83
     ignoreString
    0.82
    䙲
    0.82
    POSITIVE LOGITS
     vinto
    0.89
     sull
    0.86
     utilizza
    0.86
    izzando
    0.83
     utilizzato
    0.80
     racconta
    0.80
    esque
    0.79
    arxiv
    0.77
    That
    0.76
     concetto
    0.75
    Activations Density 0.000%

    No Known Activations